INDEX

Explanations

mention of various professions or occupations

oai_token-act-pair · gpt-3.5-turbo

occupations and their descriptions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anqu

-0.90

imar

-0.72

adas

-0.71

 TAMADRA

-0.70

chu

-0.69

atable

-0.69

ylum

-0.69

aepernick

-0.67

isSpecialOrderable

-0.67

ittens

-0.67

POSITIVE LOGITS

 accountant

1.42

 mathematician

1.39

 engineer

1.36

 psychologist

1.36

 biologist

1.34

 chemist

1.31

 technician

1.29

 lingu

1.29

 scientist

1.25

 strategist

1.25

Activations Density 0.741%

mention of various professions or occupations

occupations and their descriptions

No Comments

No Known Activations